Skip to main content
Glama
BricsCAD MCP

BricsCAD MCP

by alesdev88

bricscad_open_drawing

Open a DWG or DXF drawing and make it current for auditing; read-only by default prevents overwrites, and a timeout handles large files.

Instructions

Open a DWG or DXF and make it the current drawing. Returns the same details as bricscad_drawing_info.

path: full path to the file. read_only: true by default, so the file cannot be overwritten by accident. timeout: seconds to wait. Large drawings can take a while to open.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "path": "<path>"
    },
    "name": "bricscad_open_drawing"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYes
timeoutNo
read_onlyNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare readOnlyHint=false and destructiveHint=false, so the description adds real value: the default read_only=true protects the file from accidental overwrite, and timeout should be raised for large drawings. The notable omission is what happens to the currently open drawing and any unsaved changes when a new one becomes current — important given readOnlyHint=false means session state is mutated.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The core action and return contract are front-loaded in the first two sentences, then three short parameter notes follow. Every line carries information; no filler or repetition of the tool name.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be spelled out, and the definition correctly points at bricscad_drawing_info for shape. However, for a tool whose annotation marks it non-read-only at the session level, the description should address the fate of the previously current drawing and unsaved work.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the full burden and does so for all three parameters: path as a full filesystem path, read_only with its default and safety rationale, and timeout in seconds with the reason to increase it. It adds rationale beyond the bare schema titles, though it does not give concrete guidance on path formatting or typical timeout values for large files.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ('Open a DWG or DXF and make it the current drawing') and defines the side effect (becomes current drawing). It also cross-references bricscad_drawing_info, which distinguishes it from the pure-inspection sibling and tells the agent the return payload is redundant with that tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied rather than stated: you open a file to work on it, and the note that it returns the same details as bricscad_drawing_info hints that a follow-up info call is unnecessary. There is no explicit guidance on when to use this versus bricscad_start, bricscad_batch_run, or what to do with an already-open drawing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.